System and method for determination of object volume with multiple three-dimensional sensors

Abstract

A system and method for determining volume of a runtime object with a vision system is provided. A plurality of vision sensors are arranged so that the fields of view (FOVs) of the plurality of vision sensors collectively view features associated with volume determination of a runtime object. Each of the displacement sensors generates range images from sequences of analyzed images, each producing a single row of the range image. An ignoring volume is subtracted from the measured range image based upon one or more dividing planes as they appear in the viewing/imaging perspective of each displacement sensor. Negative subtraction results are substantially nulled. The resulting representative range images are used to calculate the volume of a portion of the object, as sectioned by the diving planes. Each volume result is summed/added to derive the overall summed volume of the runtime object.

Description

RELATED APPLICATION[0001]This application claims the benefit of U.S. Provisional Application Ser. No. 62 / 188,732, entitled SYSTEM AND METHOD FOR DETERMINATION OF OBJECT VOLUME WITH MULTIPLE THREE-DIMENSIONAL SENSORS, filed Jul. 5, 2015, the teaching of which are expressly incorporated herein by reference.FIELD OF THE INVENTION[0002]This invention relates to machine vision systems used in determining the volume of an imaged object surface using a three-dimensional (3D) sensor.BACKGROUND OF THE INVENTION[0003]In manufacturing and assembly processes, it is often desirable to analyze an object surface to determine the nature of features and / or irregularities. The displacement (or “profile”) of the object surface can be determined using a machine vision system (also termed herein “vision system”) in the form of a laser displacement sensor (also termed a laser beam “profiler”). A laser displacement sensor captures and determines the (three dimensional) profile of a scanned object surface ...

AI Technical Summary

Benefits of technology

[0009]This invention overcomes disadvantages of the prior art by providing a system and method for determination of object volume that employs at least two displacement sensors arranged so that the fields of view (FOVs) of the displacement sensors collectively image the features needed/desired to accurately determine the volume of the object. Illustratively, a calibration object (e.g. a frustum) is used at training time to define planes in physical space in the views of the two or more displacement sensors. Respective synthetic range images are generated from the calibration object images, which represent the volumes in the area between those planes and the far field of the sensors' view—wherein each sensor has its own respective range image. During runtime, each displacement sensor acquires an actual, runtime ran

Problems solved by technology

A particular challenge is measuring the volume of an object that includes su

Images